Search Results for author: Yoshiki Ito

Found 3 papers, 1 papers with code

HOKEM: Human and Object Keypoint-based Extension Module for Human-Object Interaction Detection

no code implementations25 Jun 2023 Yoshiki Ito

When processing human and object keypoints extracted from an image using a graph convolutional network (GCN) to detect HOI, it is crucial to extract appropriate object keypoints regardless of the object type and to design a GCN that accurately captures the spatial relationships between keypoints.

Human-Object Interaction Detection Object

Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter- and Intra-body Graphs

no code implementations26 Jul 2022 Yoshiki Ito, Quan Kong, Kenichi Morita, Tomoaki Yoshinaga

Skeleton-based two-person interaction recognition has been gaining increasing attention as advancements are made in pose estimation and graph convolutional networks.

Pose Estimation

Learning poly-synaptic paths with traveling waves

1 code implementation30 Nov 2019 Yoshiki Ito, Taro Toyoizumi

Traveling waves are commonly observed across the brain.

Cannot find the paper you are looking for? You can Submit a new open access paper.